Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    website links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     syair
    0.62
     iš
    0.60
    rjust
    0.59
    icollis
    0.58
     değer
    0.58
    é
    0.57
    文字列
    0.57
    úcar
    0.57
     идентифика
    0.57
    ätzlich
    0.56
    POSITIVE LOGITS
     Routine
    0.51
     Past
    0.48
     Best
    0.47
     Drift
    0.47
     Machinery
    0.46
     Multimedia
    0.46
     Archives
    0.46
    SSS
    0.46
     Mythology
    0.45
     Merchandise
    0.45
    Act Density 0.058%

    No Known Activations